[llvm-dwp] Initial partial prototype

This just concatenates the common DWP sections without doing any of the
fancy DWP things like:

1) update str_offsets
2) deduplicating strings
3) merging/creating cu/tu_index

Patches for these will follow shortly.

(also not sure about target triple/object file type for this tool - do I
really need a whole triple just to write an object file that contains
purely static/hardcoded bytes in each section? & I guess I should just
pick it based on the first input, maybe, rather than hardcoding for now
- but we only produce .dwo on ELF platforms with objcopy for now anyway)

llvm-svn: 254355

llvm/include/llvm/ADT/StringMap.h

@@ -232,6 +232,13 @@ public:
     : StringMapImpl(InitialSize, static_cast<unsigned>(sizeof(MapEntryTy))),
       Allocator(A) {}
 
+  StringMap(std::initializer_list<std::pair<StringRef, ValueTy>> List)
+      : StringMapImpl(static_cast<unsigned>(sizeof(MapEntryTy))) {
+    for (const auto &P : List) {
+      insert(P);
+    }
+  }
+
   StringMap(StringMap &&RHS)
       : StringMapImpl(std::move(RHS)), Allocator(std::move(RHS.Allocator)) {}
 

llvm/include/llvm/ADT/StringSet.h

@@ -23,6 +23,11 @@ namespace llvm {
   class StringSet : public llvm::StringMap<char, AllocatorTy> {
     typedef llvm::StringMap<char, AllocatorTy> base;
   public:
+    StringSet() = default;
+    StringSet(std::initializer_list<StringRef> S) {
+      for (StringRef X : S)
+        insert(X);
+    }
 
     std::pair<typename base::iterator, bool> insert(StringRef Key) {
       assert(!Key.empty());

llvm/test/tools/llvm-dwp/Inputs/simple/a.cpp

@@ -0,0 +1,2 @@
+struct foo { };
+foo a;

llvm/test/tools/llvm-dwp/Inputs/simple/b.cpp

@@ -0,0 +1,3 @@
+struct bar { };
+void b(bar) {
+}

llvm/test/tools/llvm-dwp/X86/lit.local.cfg

@@ -0,0 +1,4 @@
+if not 'X86' in config.root.targets:
+    config.unsupported = True
+
+config.suffixes = ['.test', '.cpp', '.m', '.s']

llvm/test/tools/llvm-dwp/X86/simple.test

@@ -0,0 +1,58 @@
+RUN: llvm-dwp %p/../Inputs/simple/a.dwo %p/../Inputs/simple/b.dwo -o %t
+RUN: llvm-dwarfdump %t | FileCheck %s
+
+FIXME: For some reason, piping straight from llvm-dwp to llvm-dwarfdump doesn't behave well - looks like dwarfdump is reading/closes before dwp has finished.
+
+DWP from non-type-unit debug info for these two translation units:
+a.cpp:
+  struct foo { };
+  foo a;
+
+b.cpp:
+  struct bar { };
+  void b(bar) {
+  }
+
+CHECK: .debug_abbrev.dwo contents:
+CHECK: Abbrev table for offset: 0x00000000
+CHECK: DW_TAG_compile_unit
+CHECK: DW_TAG_variable
+CHECK: DW_TAG_structure_type
+CHECK: Abbrev table for offset: 0x00000031
+CHECK: DW_TAG_compile_unit
+CHECK: DW_TAG_structure_type
+CHECK: DW_TAG_subprogram
+CHECK: DW_TAG_formal_parameter
+
+CHECK: .debug_info.dwo contents:
+CHECK: 0x00000000: Compile Unit: length = 0x00000025 version = 0x0004 abbr_offset = 0x0000 addr_size = 0x08 (next unit at 0x00000029)
+CHECK: DW_TAG_compile_unit
+CHECK:   DW_AT_name {{.*}} "a.cpp"
+CHECK:   DW_TAG_variable
+CHECK:     DW_AT_name {{.*}} "a"
+CHECK:   DW_TAG_structure_type
+CHECK:     DW_AT_name {{.*}} "foo"
+
+FIXME: Using cu_index, identify that abbr_offset is 0x0031, not 0x0000
+CHECK: 0x00000029: Compile Unit: length = 0x00000031 version = 0x0004 abbr_offset = 0x0000 addr_size = 0x08 (next unit at 0x0000005e)
+FIXME: Using cu_index, use strings based on the right str index offset
+CHECK:   DW_AT_name {{.*}} "a.cpp"
+FIXME: Using cu_index to find the right abbrevs at abbr_offset, this abbrevation should actually be structure_type
+CHECK:   DW_TAG_variable
+
+CHECK: .debug_cu_index contents:
+FIXME: Emit and verify the cu_index contents
+
+CHECK: .debug_str.dwo contents:
+CHECK: "clang version
+CHECK: 0x[[ACPP:.*]]: "a.cpp"
+FIXME: Remove duplicates
+CHECK: "clang version
+CHECK: 0x[[BCPP:.*]]: "b.cpp"
+
+CHECK: .debug_str_offsets.dwo contents:
+CHECK: : 00000000
+CHECK: : [[ACPP]]
+CHECK: : 00000000
+FIXME: Update str offset indexes, this should be BCPP \/
+CHECK: : [[ACPP]]

llvm/tools/llvm-dwp/llvm-dwp.cpp

@@ -1,2 +1,144 @@
-int main() {
+#include "llvm/ADT/STLExtras.h"
+#include "llvm/ADT/StringSet.h"
+#include "llvm/CodeGen/AsmPrinter.h"
+#include "llvm/MC/MCAsmInfo.h"
+#include "llvm/MC/MCContext.h"
+#include "llvm/MC/MCInstrInfo.h"
+#include "llvm/MC/MCObjectFileInfo.h"
+#include "llvm/MC/MCRegisterInfo.h"
+#include "llvm/MC/MCSectionELF.h"
+#include "llvm/MC/MCStreamer.h"
+#include "llvm/Object/ObjectFile.h"
+#include "llvm/Support/Options.h"
+#include "llvm/Support/FileSystem.h"
+#include "llvm/Support/MemoryBuffer.h"
+#include "llvm/Support/TargetRegistry.h"
+#include "llvm/Support/raw_ostream.h"
+#include "llvm/Target/TargetMachine.h"
+#include "llvm/Support/TargetSelect.h"
+#include <memory>
+#include <list>
+#include <unordered_set>
+
+using namespace llvm;
+using namespace cl;
+
+OptionCategory DwpCategory("Specific Options");
+static list<std::string> InputFiles(Positional, OneOrMore,
+                                    desc("<input files>"), cat(DwpCategory));
+
+static opt<std::string> OutputFilename(Required, "o", desc("Specify the output file."),
+                                      value_desc("filename"), cat(DwpCategory));
+
+static int error(const Twine &Error, const Twine &Context) {
+  errs() << Twine("while processing ") + Context + ":\n";
+  errs() << Twine("error: ") + Error + "\n";
+  return 1;
+}
+
+static std::error_code writeSection(MCStreamer &Out, MCSection *OutSection,
+                                    const object::SectionRef &Sym) {
+  StringRef Contents;
+  if (auto Err = Sym.getContents(Contents))
+    return Err;
+  Out.SwitchSection(OutSection);
+  Out.EmitBytes(Contents);
+  return std::error_code();
+}
+
+static std::error_code write(MCStreamer &Out, ArrayRef<std::string> Inputs) {
+  for (const auto &Input : Inputs) {
+    auto ErrOrObj = object::ObjectFile::createObjectFile(Input);
+    if (!ErrOrObj)
+      return ErrOrObj.getError();
+    const auto *Obj = ErrOrObj->getBinary();
+    for (const auto &Section : Obj->sections()) {
+      const auto &MCOFI = *Out.getContext().getObjectFileInfo();
+      static const StringMap<MCSection *> KnownSections = {
+          {"debug_info.dwo", MCOFI.getDwarfInfoDWOSection()},
+          {"debug_types.dwo", MCOFI.getDwarfTypesDWOSection()},
+          {"debug_str_offsets.dwo", MCOFI.getDwarfStrOffDWOSection()},
+          {"debug_str.dwo", MCOFI.getDwarfStrDWOSection()},
+          {"debug_loc.dwo", MCOFI.getDwarfLocDWOSection()},
+          {"debug_abbrev.dwo", MCOFI.getDwarfAbbrevDWOSection()}};
+      StringRef Name;
+      if (std::error_code Err = Section.getName(Name))
+        return Err;
+      if (MCSection *OutSection =
+              KnownSections.lookup(Name.substr(Name.find_first_not_of("._"))))
+        if (auto Err = writeSection(Out, OutSection, Section))
+          return Err;
+    }
+  }
+  return std::error_code();
+}
+
+int main(int argc, char** argv) {
+
+  ParseCommandLineOptions(argc, argv, "merge split dwarf (.dwo) files");
+
+  llvm::InitializeAllTargetInfos();
+  llvm::InitializeAllTargetMCs();
+  llvm::InitializeAllTargets();
+  llvm::InitializeAllAsmPrinters();
+
+  std::string ErrorStr;
+  StringRef Context = "dwarf streamer init";
+
+  Triple TheTriple("x86_64-linux-gnu");
+
+  // Get the target.
+  const Target *TheTarget =
+      TargetRegistry::lookupTarget("", TheTriple, ErrorStr);
+  if (!TheTarget)
+    return error(ErrorStr, Context);
+  std::string TripleName = TheTriple.getTriple();
+
+  // Create all the MC Objects.
+  std::unique_ptr<MCRegisterInfo> MRI(TheTarget->createMCRegInfo(TripleName));
+  if (!MRI)
+    return error(Twine("no register info for target ") + TripleName, Context);
+
+  std::unique_ptr<MCAsmInfo> MAI(TheTarget->createMCAsmInfo(*MRI, TripleName));
+  if (!MAI)
+    return error("no asm info for target " + TripleName, Context);
+
+  MCObjectFileInfo MOFI;
+  MCContext MC(MAI.get(), MRI.get(), &MOFI);
+  MOFI.InitMCObjectFileInfo(TheTriple, Reloc::Default, CodeModel::Default,
+                             MC);
+
+  auto MAB = TheTarget->createMCAsmBackend(*MRI, TripleName, "");
+  if (!MAB)
+    return error("no asm backend for target " + TripleName, Context);
+
+  std::unique_ptr<MCInstrInfo> MII(TheTarget->createMCInstrInfo());
+  if (!MII)
+    return error("no instr info info for target " + TripleName, Context);
+
+  std::unique_ptr<MCSubtargetInfo> MSTI(
+      TheTarget->createMCSubtargetInfo(TripleName, "", ""));
+  if (!MSTI)
+    return error("no subtarget info for target " + TripleName, Context);
+
+  MCCodeEmitter *MCE = TheTarget->createMCCodeEmitter(*MII, *MRI, MC);
+  if (!MCE)
+    return error("no code emitter for target " + TripleName, Context);
+
+  // Create the output file.
+  std::error_code EC;
+  raw_fd_ostream OutFile(OutputFilename, EC, sys::fs::F_None);
+  if (EC)
+    return error(Twine(OutputFilename) + ": " + EC.message(), Context);
+
+  std::unique_ptr<MCStreamer> MS(TheTarget->createMCObjectStreamer(
+      TheTriple, MC, *MAB, OutFile, MCE, *MSTI, false,
+      /*DWARFMustBeAtTheEnd*/ false));
+  if (!MS)
+    return error("no object streamer for target " + TripleName, Context);
+
+  if (auto Err = write(*MS, InputFiles))
+    return error(Err.message(), "Writing DWP file");
+
+  MS->Finish();
 }